🏆
Rankings
LLM Leaderboard
Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.
⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,23 tok/s TG Prefill 904 · TTFT 15.542 ms | 5× | NVIDIA Tesla V100 PCIe 32GB4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | strataIQ3_S | Details → | |
| 2 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,09 tok/s TG Prefill 1.023 · TTFT 43.363 ms | 10× | NVIDIA Tesla V100 PCIe 32GB4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | strataIQ3_S | Details → | |
| 3 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,28 tok/s TG Prefill 483 · TTFT 4.084 ms | 1× | NVIDIA Tesla V100 PCIe 32GB4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | strataIQ3_S | Details → |